kailuokk / siamgat

Code for the paper "Graph Attention Tracking". (CVPR2021)

SiamGAT

1. Environment setup

This code has been tested on Ubuntu 16.04, Python 3.5, Pytorch 1.2.0, CUDA 9.0. Please install related libraries before running this code:

pip install -r requirements.txt

2. Test

Dataset		SiamGAT	Model Link
OTB100	Success	71.0	Google Driver/ BaiduYun(w1rs)
	Precision	91.7
UAV123	Success	64.6
	Precision	84.3
LaSOT	Success	53.9	Google Driver/ BaiduYun(dilp)
	Norm precision	63.3
	Precision	53.0
GOT10k	AO	63.1	Google Driver/ BaiduYun(zktx)
	SR0.5	74.6
	SR0.75	50.4
TrackingNet	Success	75.3	Google Driver/ BaiduYun(n2sm)
	Norm precision	80.7
	Precision	69.8

Download testing datasets and put them into test_dataset directory. Jsons of commonly used datasets can be downloaded from BaiduYun. If you want to test the tracker on a new dataset, please refer to pysot-toolkit to set test_dataset.

The tracking result can be download from BaiduYun (extract code: 5o17) or GoogleDriver for comparision.

python testTracker.py \    
        --config ../experiments/siamgat_googlenet_otb_uav/config.yaml \
	--dataset UAV123 \                                 # dataset_name
	--snapshot snapshot/otb_uav_model.pth              # tracker_name

The testing result will be saved in the results/dataset_name/tracker_name directory.

3. Train

Prepare training datasets

Download the datasets：

• VID
• YOUTUBEBB (code: v7s6)
• DET
• COCO
• GOT-10K
• LaSOT
• TrackingNet

Note: training_dataset/dataset_name/readme.md has listed detailed operations about how to generate training datasets.

Download pretrained backbones

Download pretrained backbones from link and put them into pretrained_models directory.

Train a model

To train the SiamGAT model, run train.py with the desired configs:

cd tools
python train.py

4. Evaluation

We provide the tracking results (extract code: 0wod) (results in Google driver) of GOT-10k, LaSOT, OTB100 and UAV123. If you want to evaluate the tracker on OTB100, UAV123 and LaSOT, please put those results into results directory. Evaluate GOT-10k on Server.
Get TrackingNet results from BaiduYun (extract code: iwlj), and evaluate it on Server.

python eval.py 	                          \
	--tracker_path ./results          \ # result path
	--dataset UAV123                  \ # dataset_name
	--tracker_prefix 'otb_uav_model'   # tracker_name

5. Acknowledgement

The code is implemented based on pysot and SiamCAR. We would like to express our sincere thanks to the contributors.

6. Cite

If you use SiamGAT in your work please cite our papers:

@article{cui2022joint,
title={Joint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks},
author={Cui, Ying and Guo, Dongyan and Shao, Yanyan and Wang, Zhenhua and Shen, Chunhua and Zhang, Liyan and Chen, Shengyong},
journal={International Journal of Computer Vision},
year={2022},
publisher={Springer},
doi = {10.1007/s11263-021-01559-4}
}

@InProceedings{Guo_2021_CVPR,
author = {Guo, Dongyan and Shao, Yanyan and Cui, Ying and Wang, Zhenhua and Zhang, Liyan and Shen, Chunhua},
title = {Graph Attention Tracking},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021}
}

@InProceedings{Guo_2020_CVPR,
author = {Guo, Dongyan and Wang, Jun and Cui, Ying and Wang, Zhenhua and Chen, Shengyong},
title = {SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}